Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 2620
    Prev
    Next
    INDEX
    Explanations

    repeated sequences of equal signs, likely for formatting or structural emphasis in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    *********
    -0.99
    *************
    -0.96
    *********/
    -0.95
    ************
    -0.94
    ***********
    -0.94
    ********
    -0.90
    **********
    -0.88
     {*}
    -0.88
     }^{*}
    -0.88
    ***************
    -0.87
    POSITIVE LOGITS
    ================
    2.19
    ————————————————
    1.05
    ----------------
    1.04
    ~~~~~~~~~~~~~~~~
    0.86
    ################
    0.86
    ————————
    0.84
    ________________
    0.83
    ................
    0.83
    ▬▬▬▬▬▬▬▬
    0.78
    qu
    0.78
    Activations Density 0.215%

    No Known Activations